rdt 1.15.1.dev0__tar.gz → 1.16.0.dev0__tar.gz

{rdt-1.15.1.dev0/rdt.egg-info → rdt-1.16.0.dev0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rdt
-Version: 1.15.1.dev0
+Version: 1.16.0.dev0
 Summary: Reversible Data Transforms
 Author-email: "DataCebo, Inc." <info@sdv.dev>
 License: BSL-1.1
@@ -53,23 +53,24 @@ Requires-Dist: rdt[copulas]; extra == "test"
 Requires-Dist: pytest>=3.4.2; extra == "test"
 Requires-Dist: pytest-cov>=2.6.0; extra == "test"
 Requires-Dist: jupyter<2,>=1.0.0; extra == "test"
-Requires-Dist: rundoc<0.5,>=0.4.3; extra == "test"
 Requires-Dist: pytest-subtests<1.0,>=0.5; extra == "test"
 Requires-Dist: pytest-runner>=2.11.1; extra == "test"
 Requires-Dist: tomli<3,>=2.0.0; extra == "test"
 Provides-Extra: dev
 Requires-Dist: rdt[test]; extra == "dev"
 Requires-Dist: build<2,>=1.0.0; extra == "dev"
-Requires-Dist: bump-my-version<1,>=0.18.3; extra == "dev"
+Requires-Dist: bump-my-version>=0.18.3; extra == "dev"
 Requires-Dist: pip>=9.0.1; extra == "dev"
 Requires-Dist: watchdog<5,>=1.0.1; extra == "dev"
 Requires-Dist: ruff<1,>=0.3.2; extra == "dev"
-Requires-Dist: twine<6,>=1.10.0; extra == "dev"
+Requires-Dist: twine>=1.10.0; extra == "dev"
 Requires-Dist: wheel>=0.30.0; extra == "dev"
 Requires-Dist: coverage<8,>=4.5.12; extra == "dev"
 Requires-Dist: tox<5,>=2.9.1; extra == "dev"
 Requires-Dist: tabulate<1,>=0.8.9; extra == "dev"
 Requires-Dist: invoke; extra == "dev"
+Provides-Extra: readme
+Requires-Dist: rundoc<0.5,>=0.4.3; extra == "readme"
 Dynamic: license-file
 
 <div align="center">

{rdt-1.15.1.dev0 → rdt-1.16.0.dev0}/pyproject.toml

@@ -54,7 +54,7 @@ rdt = { main = 'rdt.cli.__main__:main' }
 
 [project.optional-dependencies]
 copulas = ['copulas>=0.12.1',]
-pyarrow = ['pyarrow>=17.0.0']
+pyarrow = ['pyarrow>=17.0.0',]
 test = [
     'rdt[pyarrow]',
     'rdt[copulas]',
@@ -62,7 +62,6 @@ test = [
     'pytest>=3.4.2',
     'pytest-cov>=2.6.0',
     'jupyter>=1.0.0,<2',
-    'rundoc>=0.4.3,<0.5',
     'pytest-subtests>=0.5,<1.0',
     'pytest-runner >= 2.11.1',
     'tomli>=2.0.0,<3',
@@ -72,7 +71,7 @@ dev = [
 
     # general
     'build>=1.0.0,<2',
-    'bump-my-version>=0.18.3,<1',
+    'bump-my-version>=0.18.3',
     'pip>=9.0.1',
     'watchdog>=1.0.1,<5',
 
@@ -80,7 +79,7 @@ dev = [
     'ruff>=0.3.2,<1',
 
     # distribute on PyPI
-    'twine>=1.10.0,<6',
+    'twine>=1.10.0',
     'wheel>=0.30.0',
 
     # Advanced testing
@@ -89,8 +88,9 @@ dev = [
     'tabulate>=0.8.9,<1',
 
     # Invoking test commands
-    'invoke'
+    'invoke',
 ]
+readme = ['rundoc>=0.4.3,<0.5',]
 
 [tool.setuptools]
 include-package-data = true
@@ -144,7 +144,7 @@ collect_ignore = ['pyproject.toml']
 exclude_lines = ['NotImplementedError()']
 
 [tool.bumpversion]
-current_version = "1.15.1.dev0"
+current_version = "1.16.0.dev0"
 parse = '(?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\.(?P<release>[a-z]+)(?P<candidate>\d+))?'
 serialize = [
     '{major}.{minor}.{patch}.{release}{candidate}',

{rdt-1.15.1.dev0 → rdt-1.16.0.dev0}/rdt/__init__.py

@@ -4,7 +4,7 @@
 
 __author__ = 'DataCebo, Inc.'
 __email__ = 'info@sdv.dev'
-__version__ = '1.15.1.dev0'
+__version__ = '1.16.0.dev0'
 
 
 import sys

{rdt-1.15.1.dev0 → rdt-1.16.0.dev0}/rdt/transformers/__init__.py

@@ -22,7 +22,7 @@ from rdt.transformers.datetime import (
     OptimizedTimestampEncoder,
     UnixTimestampEncoder,
 )
-from rdt.transformers.id import IDGenerator, RegexGenerator
+from rdt.transformers.id import IDGenerator, IndexGenerator, RegexGenerator
 from rdt.transformers.null import NullTransformer
 from rdt.transformers.numerical import (
     ClusterBasedNormalizer,
@@ -57,6 +57,7 @@ __all__ = [
     'AnonymizedFaker',
     'PseudoAnonymizedFaker',
     'IDGenerator',
+    'IndexGenerator',
     'get_transformer_name',
     'get_transformer_class',
     'get_transformers_by_type',

{rdt-1.15.1.dev0 → rdt-1.16.0.dev0}/rdt/transformers/categorical.py

@@ -40,7 +40,7 @@ class UniformEncoder(BaseTransformer):
     """
 
     INPUT_SDTYPE = 'categorical'
-    SUPPORTED_SDTYPES = ['categorical', 'boolean']
+    SUPPORTED_SDTYPES = ['categorical', 'boolean', 'id', 'text']
     frequencies = None
     intervals = None
     dtype = None
@@ -733,7 +733,7 @@ class LabelEncoder(BaseTransformer):
     """
 
     INPUT_SDTYPE = 'categorical'
-    SUPPORTED_SDTYPES = ['categorical', 'boolean']
+    SUPPORTED_SDTYPES = ['categorical', 'boolean', 'id', 'text']
     values_to_categories = None
     categories_to_values = None
     dtype = 'O'

{rdt-1.15.1.dev0 → rdt-1.16.0.dev0}/rdt/transformers/id.py

@@ -7,12 +7,15 @@ import numpy as np
 import pandas as pd
 
 from rdt.transformers.base import BaseTransformer
-from rdt.transformers.utils import strings_from_regex
+from rdt.transformers.utils import (
+    _handle_enforce_uniqueness_and_cardinality_rule,
+    strings_from_regex,
+)
 
 LOGGER = logging.getLogger(__name__)
 
 
-class IDGenerator(BaseTransformer):
+class IndexGenerator(BaseTransformer):
     """Generate an ID column.
 
     This transformer generates an ID column based on a given prefix, starting value and suffix.
@@ -72,6 +75,21 @@ class IDGenerator(BaseTransformer):
         return pd.Series(values)
 
 
+class IDGenerator(IndexGenerator):
+    """Deprecated class name for ``IndexGenerator``.
+
+    Class to ensure backwards compatibility with previous versions of RDT.
+    """
+
+    def __init__(self, prefix=None, starting_value=0, suffix=None):
+        warnings.warn(
+            "The 'IDGenerator' has been renamed to 'IndexGenerator'. Please update the"
+            'name to ensure compatibility with future versions of RDT.',
+            FutureWarning,
+        )
+        super().__init__(prefix, starting_value, suffix)
+
+
 class RegexGenerator(BaseTransformer):
     """RegexGenerator transformer.
 
@@ -82,9 +100,13 @@ class RegexGenerator(BaseTransformer):
         regex (str):
             String representing the regex function.
         enforce_uniqueness (bool):
-            Whether or not to ensure that the new generated data is all unique. If it isn't
-            possible to create the requested number of rows, then an error will be raised.
-            Defaults to ``False``.
+            **DEPRECATED** Whether or not to ensure that the new generated data is all unique.
+            If it isn't possible to create the requested number of rows, then an error will
+            be raised. Defaults to ``None``.
+        cardinality_rule (str):
+            Rule that the generated data must follow. If set to ``unique``, the generated
+            data must be unique. If set to ``None``, then the generated data may contain
+            duplicates. Defaults to ``None``.
         generation_order (str):
             String defining how to generate the output. If set to ``alphanumeric``, it will
             generate the output in alphanumeric order (ie. 'aaa', 'aab' or '1', '2'...). If
@@ -122,13 +144,16 @@ class RegexGenerator(BaseTransformer):
     def __init__(
         self,
         regex_format='[A-Za-z]{5}',
-        enforce_uniqueness=False,
+        cardinality_rule=None,
         generation_order='alphanumeric',
+        enforce_uniqueness=None,
     ):
         super().__init__()
         self.output_properties = {None: {'next_transformer': None}}
-        self.enforce_uniqueness = enforce_uniqueness
         self.regex_format = regex_format
+        self.cardinality_rule = _handle_enforce_uniqueness_and_cardinality_rule(
+            enforce_uniqueness, cardinality_rule
+        )
         self.data_length = None
         self.generator = None
         self.generator_size = None
@@ -158,16 +183,18 @@ class RegexGenerator(BaseTransformer):
         """Drop the input column by returning ``None``."""
         return None
 
-    def _warn_not_enough_unique_values(self, sample_size):
+    def _warn_not_enough_unique_values(self, sample_size, unique_condition):
         """Warn the user that the regex cannot generate enough unique values.
 
         Args:
             sample_size (int):
                 Number of samples to be generated.
+            unique_condition (bool):
+                Whether or not to enforce uniqueness.
         """
         warned = False
         if sample_size > self.generator_size:
-            if self.enforce_uniqueness:
+            if unique_condition:
                 warnings.warn(
                     f"The regex for '{self.get_input_column()}' can only generate "
                     f'{self.generator_size} unique values. Additional values may not exactly '
@@ -185,7 +212,7 @@ class RegexGenerator(BaseTransformer):
                 )
 
         remaining = self.generator_size - self.generated
-        if sample_size > remaining and self.enforce_uniqueness and not warned:
+        if sample_size > remaining and unique_condition and not warned:
             warnings.warn(
                 f'The regex generator is not able to generate {sample_size} new unique '
                 f'values (only {max(remaining, 0)} unique values left).'
@@ -201,12 +228,17 @@ class RegexGenerator(BaseTransformer):
         Returns:
             pandas.Series
         """
+        if hasattr(self, 'cardinality_rule'):
+            unique_condition = self.cardinality_rule == 'unique'
+        else:
+            unique_condition = self.enforce_uniqueness
+
         if data is not None and len(data):
             sample_size = len(data)
         else:
             sample_size = self.data_length
 
-        self._warn_not_enough_unique_values(sample_size)
+        self._warn_not_enough_unique_values(sample_size, unique_condition)
 
         remaining = self.generator_size - self.generated
         if sample_size > remaining:
@@ -225,7 +257,7 @@ class RegexGenerator(BaseTransformer):
         reverse_transformed = generated_values[:]
 
         if len(reverse_transformed) < sample_size:
-            if self.enforce_uniqueness:
+            if unique_condition:
                 try:
                     remaining_samples = sample_size - len(reverse_transformed)
                     start = int(generated_values[-1]) + 1

{rdt-1.15.1.dev0 → rdt-1.16.0.dev0}/rdt/transformers/pii/anonymizer.py

@@ -15,6 +15,7 @@ import pandas as pd
 from rdt.errors import TransformerInputError, TransformerProcessingError
 from rdt.transformers.base import BaseTransformer
 from rdt.transformers.categorical import LabelEncoder
+from rdt.transformers.utils import _handle_enforce_uniqueness_and_cardinality_rule
 
 
 class AnonymizedFaker(BaseTransformer):
@@ -113,7 +114,7 @@ class AnonymizedFaker(BaseTransformer):
         function_kwargs=None,
         locales=None,
         cardinality_rule=None,
-        enforce_uniqueness=False,
+        enforce_uniqueness=None,
         missing_value_generation='random',
     ):
         super().__init__()
@@ -121,14 +122,9 @@ class AnonymizedFaker(BaseTransformer):
         self.data_length = None
         self.enforce_uniqueness = enforce_uniqueness
         self.cardinality_rule = cardinality_rule.lower() if cardinality_rule else None
-        if enforce_uniqueness:
-            warnings.warn(
-                "The 'enforce_uniqueness' parameter is no longer supported. "
-                "Please use the 'cardinality_rule' parameter instead.",
-                FutureWarning,
-            )
-            if not self.cardinality_rule:
-                self.cardinality_rule = 'unique'
+        self.cardinality_rule = _handle_enforce_uniqueness_and_cardinality_rule(
+            enforce_uniqueness, cardinality_rule
+        )
 
         self.provider_name = provider_name if provider_name else 'BaseProvider'
         if self.provider_name != 'BaseProvider' and function_name is None:

{rdt-1.15.1.dev0 → rdt-1.16.0.dev0}/rdt/transformers/utils.py

@@ -369,3 +369,17 @@ class WarnDict(dict):
         phased out.
         """
         return self.get(sdtype)
+
+
+def _handle_enforce_uniqueness_and_cardinality_rule(enforce_uniqueness, cardinality_rule):
+    result = cardinality_rule
+    if enforce_uniqueness is not None:
+        warnings.warn(
+            "The 'enforce_uniqueness' parameter is no longer supported. "
+            "Please use the 'cardinality_rule' parameter instead.",
+            FutureWarning,
+        )
+        if enforce_uniqueness and cardinality_rule is None:
+            result = 'unique'
+
+    return result

{rdt-1.15.1.dev0 → rdt-1.16.0.dev0/rdt.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rdt
-Version: 1.15.1.dev0
+Version: 1.16.0.dev0
 Summary: Reversible Data Transforms
 Author-email: "DataCebo, Inc." <info@sdv.dev>
 License: BSL-1.1
@@ -53,23 +53,24 @@ Requires-Dist: rdt[copulas]; extra == "test"
 Requires-Dist: pytest>=3.4.2; extra == "test"
 Requires-Dist: pytest-cov>=2.6.0; extra == "test"
 Requires-Dist: jupyter<2,>=1.0.0; extra == "test"
-Requires-Dist: rundoc<0.5,>=0.4.3; extra == "test"
 Requires-Dist: pytest-subtests<1.0,>=0.5; extra == "test"
 Requires-Dist: pytest-runner>=2.11.1; extra == "test"
 Requires-Dist: tomli<3,>=2.0.0; extra == "test"
 Provides-Extra: dev
 Requires-Dist: rdt[test]; extra == "dev"
 Requires-Dist: build<2,>=1.0.0; extra == "dev"
-Requires-Dist: bump-my-version<1,>=0.18.3; extra == "dev"
+Requires-Dist: bump-my-version>=0.18.3; extra == "dev"
 Requires-Dist: pip>=9.0.1; extra == "dev"
 Requires-Dist: watchdog<5,>=1.0.1; extra == "dev"
 Requires-Dist: ruff<1,>=0.3.2; extra == "dev"
-Requires-Dist: twine<6,>=1.10.0; extra == "dev"
+Requires-Dist: twine>=1.10.0; extra == "dev"
 Requires-Dist: wheel>=0.30.0; extra == "dev"
 Requires-Dist: coverage<8,>=4.5.12; extra == "dev"
 Requires-Dist: tox<5,>=2.9.1; extra == "dev"
 Requires-Dist: tabulate<1,>=0.8.9; extra == "dev"
 Requires-Dist: invoke; extra == "dev"
+Provides-Extra: readme
+Requires-Dist: rundoc<0.5,>=0.4.3; extra == "readme"
 Dynamic: license-file
 
 <div align="center">

{rdt-1.15.1.dev0 → rdt-1.16.0.dev0}/rdt.egg-info/requires.txt

@@ -37,11 +37,11 @@ copulas>=0.12.1
 [dev]
 rdt[test]
 build<2,>=1.0.0
-bump-my-version<1,>=0.18.3
+bump-my-version>=0.18.3
 pip>=9.0.1
 watchdog<5,>=1.0.1
 ruff<1,>=0.3.2
-twine<6,>=1.10.0
+twine>=1.10.0
 wheel>=0.30.0
 coverage<8,>=4.5.12
 tox<5,>=2.9.1
@@ -51,13 +51,15 @@ invoke
 [pyarrow]
 pyarrow>=17.0.0
 
+[readme]
+rundoc<0.5,>=0.4.3
+
 [test]
 rdt[pyarrow]
 rdt[copulas]
 pytest>=3.4.2
 pytest-cov>=2.6.0
 jupyter<2,>=1.0.0
-rundoc<0.5,>=0.4.3
 pytest-subtests<1.0,>=0.5
 pytest-runner>=2.11.1
 tomli<3,>=2.0.0

{rdt-1.15.1.dev0 → rdt-1.16.0.dev0}/rdt/transformers/datetime.py

@@ -210,10 +210,10 @@ class UnixTimestampEncoder(BaseTransformer):
         Returns:
             pandas.Series
         """
+        data = self._reverse_transform_helper(data)
         if self.enforce_min_max_values:
             data = data.clip(self._min_value, self._max_value)
 
-        data = self._reverse_transform_helper(data)
         datetime_data = pd.to_datetime(data)
         if self.datetime_format:
             if is_datetime64_dtype(self._dtype) and '.%f' not in self.datetime_format: